Runtime vs Tensorlake Sandboxes
Runtime costs $0.025 per vCPU-hour and Tensorlake Sandboxes costs $0.07 per vCPU-hour. Runtime runs Firecracker microVMs and has no session limit. Tensorlake Sandboxes runs Firecracker microVMs, offers GPUs and has no session limit.
Updated
Runtime
- Isolation
- Firecracker microVM
- Free tier
- 100 hours of a 1 GB machine in the first 30 days
- Max session
- No limit
Tensorlake Sandboxes
- Isolation
- Firecracker microVM
- Free tier
- Free plan, $0 forever
- Max session
- No limit
What is different
9 fields differ. The rest are the same or not listed.
Runtime
Tensorlake Sandboxes
- vCPU, per hour
- Runtime: $0.025
- Tensorlake Sandboxes: $0.07
- RAM, per GiB-hour
- Runtime: $0.0075
- Tensorlake Sandboxes: $0.015
- Storage
- Runtime: $0.000119 per GiB-hour after 10 free GiB
- Tensorlake Sandboxes: $0.0002 per GiB-hour
- Free tier
- Runtime: 100 hours of a 1 GB machine in the first 30 days
- Tensorlake Sandboxes: Free plan, $0 forever
- Idle stop
- Runtime: After 5 minutes
- Tensorlake Sandboxes: After 10 minutes
- Concurrent sandboxes
- Runtime: Up to 200
- Tensorlake Sandboxes: Up to 1,000
- GPU
- Runtime: No
- Tensorlake Sandboxes:
- SDKs
- Runtime: JavaScript / TypeScript, Python, Go, Ruby, Java
- Tensorlake Sandboxes: Python, TypeScript
- Integrations
- Runtime: OpenAI Agents SDK, Vercel AI SDK, Claude Agent SDK, LangChain, MCP, Claude Code
- Tensorlake Sandboxes: OpenAI Agents SDK
Full comparison
18 fields, at each provider's list price
Runtimewithruntime
Tensorlake Sandboxestensorlake
Pricing
- vCPU, per hour
- Runtime: $0.025
- Tensorlake Sandboxes: $0.07
- RAM, per GiB-hour
- Runtime: $0.0075
- Tensorlake Sandboxes: $0.015
- Storage
- Runtime: $0.000119 per GiB-hour after 10 free GiB
- Tensorlake Sandboxes: $0.0002 per GiB-hour
- Free tier
- Runtime: 100 hours of a 1 GB machine in the first 30 days
- Tensorlake Sandboxes: Free plan, $0 forever
- Paid plan from
- Runtime: Pay as you go
- Tensorlake Sandboxes: Pay as you go
- Billing
- Runtime: Active CPU time only
- Tensorlake Sandboxes: Active CPU time only
Limits
- Max session
- Runtime: No limit
- Tensorlake Sandboxes: No limit
- Idle stop
- Runtime: After 5 minutes
- Tensorlake Sandboxes: After 10 minutes
- Largest sandbox
- Runtime: 16 vCPU · 64 GiB
- Tensorlake Sandboxes: 16 vCPU · 64 GiB
- Concurrent sandboxes
- Runtime: Up to 200
- Tensorlake Sandboxes: Up to 1,000
Platform
- Isolation
- Runtime: Firecracker microVM
- Tensorlake Sandboxes: Firecracker microVM
- GPU
- Runtime: No
- Tensorlake Sandboxes:
- Snapshots
- Runtime:
- Tensorlake Sandboxes:
- Pause and resume
- Runtime:
- Tensorlake Sandboxes:
Developer
- SDKs
- Runtime: JavaScript / TypeScript, Python, Go, Ruby, Java
- Tensorlake Sandboxes: Python, TypeScript
- Integrations
- Runtime: OpenAI Agents SDK, Vercel AI SDK, Claude Agent SDK, LangChain, MCP, Claude Code
- Tensorlake Sandboxes: OpenAI Agents SDK
Trust
- License
- Runtime: Not listed
- Tensorlake Sandboxes: Not listed
- BYOC
- Runtime: Not listed
- Tensorlake Sandboxes: AWS, GCP, Azure, CoreWeave, Nebius or bare metal
Hourly cost
One sandbox running for one hour
Runtime
Tensorlake Sandboxes
- 1 vCPU · 2 GiB
- Runtime: $0.040
- Tensorlake Sandboxes: $0.100
- 2 vCPU · 4 GiB
- Runtime: $0.080
- Tensorlake Sandboxes: $0.200
- 4 vCPU · 8 GiB
- Runtime: $0.160
- Tensorlake Sandboxes: $0.400
Compute only, at list rates.
Open the calculatorWhich one fits
Based on the fields above
Runtime fits when
- You use the Vercel AI SDK, the Claude Agent SDK, LangChain, MCP or Claude Code.
- You want the lower list price: $0.080 against $0.200 an hour for 2 vCPU and 4 GiB.
Tensorlake Sandboxes fits when
- You need GPUs.
- You need the sandboxes in your own cloud account.
- You need SOC 2 Type II and HIPAA.
More comparisons
Agent Sandbox vs Runtime- Agent Sandbox vs Tensorlake Sandboxes
Agent37 Cloud vs Runtime- Agent37 Cloud vs Tensorlake Sandboxes
AgentBay vs Runtime- AgentBay vs Tensorlake Sandboxes
- Alibaba Cloud Agent Sandbox vs Runtime
- Alibaba Cloud Agent Sandbox vs Tensorlake Sandboxes